<div dir="ltr">Dear Stephan,<div><br></div><div>please find below the requested high-level information (sorry about the delay). For DSyntS and PredArg we used rule-based modules so there is no training data, but since they both include the surface parser as a first step, I'm not sure if putting a non-applicable or repeat the SSynt information. About the last column, we have no other publications which contains more information about the modules as we used them.<br><br><table cellspacing="0" cellpadding="0" dir="ltr" border="1" style="table-layout:fixed;font-size:10pt;font-family:arial,sans,sans-serif;width:0px;border-collapse:collapse;border:none"><colgroup><col width="107"><col width="52"><col width="191"><col width="175"><col width="69"><col width="52"><col width="105"></colgroup><tbody><tr style="height:21px"><td style="border-top-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">upf</td><td style="border-top-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom;text-align:center">0</td><td style="border-top-color:rgb(0,0,0);border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">SSyntS</td><td style="border-top-color:rgb(0,0,0);border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom"><span style="font-size:10pt;font-family:Arial">WSJ 02–21</span></td><td style="border-top-color:rgb(0,0,0);border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">958,167</td><td style="border-top-color:rgb(0,0,0);border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">txt</td><td style="border-top-color:rgb(0,0,0);border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">CoNLL'09</td></tr><tr style="height:21px"><td style="overflow:hidden;padding:2px 3px;vertical-align:bottom">upf</td><td style="overflow:hidden;padding:2px 3px;vertical-align:bottom;text-align:center">1</td><td style="border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">DSyntS</td><td style="border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">N/A?</td><td style="border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">N/A?</td><td style="border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">txt</td><td style="border-right-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom"></td></tr><tr style="height:21px"><td style="border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">upf</td><td style="border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom;text-align:center">2</td><td style="border-right-color:rgb(0,0,0);border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">PredArg</td><td style="border-right-color:rgb(0,0,0);border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">N/A?</td><td style="border-right-color:rgb(0,0,0);border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">N/A?</td><td style="border-right-color:rgb(0,0,0);border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom">txt</td><td style="border-right-color:rgb(0,0,0);border-bottom-color:rgb(0,0,0);overflow:hidden;padding:2px 3px;vertical-align:bottom"></td></tr></tbody></table></div><div class="gmail_extra"><br><div class="gmail_quote">I also attach the paper with the description of our submissions.</div><div class="gmail_quote">Best,</div><div class="gmail_quote"><br></div><div class="gmail_quote">simon</div><div class="gmail_quote"><br></div><div class="gmail_quote">On Tue, Aug 8, 2017 at 12:20 PM, Stephan Oepen <span dir="ltr"><<a href="mailto:oe@ifi.uio.no" target="_blank">oe@ifi.uio.no</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">colleagues,<br> <br> in preparing our task summary, and to support everyone in trying to<br> interpret our empirical results, we would like to gather some<br> high-level information about all participating systems, viz. for each<br> run:<br> <br> (0) representation: brief characterization of the type of<br> dependencies, e.g. LTH, DM, UD, etc.<br> (1) training: source (nature) of your training data, e.g. PTB<br> converted by CoreNLP 3.3.1.<br> (2) tokens: size of the training data, in tokens (according to your<br> tokenization scheme).<br> (3) input: whether the parser operated on ‘raw’ texts or our<br> pre-processed input files.<br> (4) reference: a pointer (web link or bibliographic reference) to more<br> background.<br> <br> —we have added these columns to our master spreadsheet; see:<br> <br> <a href="http://goo.gl/ZTZxXW" rel="noreferrer" target="_blank">http://goo.gl/ZTZxXW</a><br> <br> in some cases, i was able to make informed guesses from the README<br> files provided with each run. but there is a lot of information<br> missing that i would like to ask each team to fill in, preferably over<br> the next few days.<br> <br> could one representative per team please quickly email<br> ‘epe-organizers’ what you would like to appear for your submissions<br> for questions (0) to (4) above?<br> <br> semi-relatedly, thanks to everyone who has filled in our short<br> questionnaire about how to best wrap up EPE 2017 and plan for the<br> future. a few teams are still missing, and we would like to share a<br> summary with everyone at the end of this week.<br> <br> if you have not done so already, please take a minute and provide your<br> perspective to us:<br> <br> <a href="http://goo.gl/tpDK3o" rel="noreferrer" target="_blank">http://goo.gl/tpDK3o</a><br> <br> best wishes, oe<br> <br> </blockquote></div><br></div></div>